Automatic PV production profile generation using geographic and historical weather data

This paper introduces on a probabilistic model to automatically generate photovoltaic production profiles for a given geographical region and future scenarios for deployment of renewable energy resources. The model for these profiles uses local properties of buildings, demographic statistics, and historical weather data. Sub-models are calibrated with actual PV data from a smart grid pilot site in the Netherlands and literature based scenarios. It is shown that the model performs adequately and the results are compared with historical data of photovoltaic installations.

[1]  Giuseppina Ciulla,et al.  Artificial Neural Networks to Predict the Power Output of a PV Panel , 2014 .

[2]  R. A. Verzijlbergh,et al.  The Power of Electric Vehicles - Exploring the Value of Flexible Electricity Demand in a Multi-actor Context , 2013 .

[3]  E Else Veldman,et al.  Power play : impacts of flexibility in future residential electricity demand on distribution network utilisation , 2013 .

[4]  Han Slootweg,et al.  A flexible, privacy enhanced and secured ict architecture for a smart grid project with active consumers in the city of Zwolle, NL , 2013 .

[5]  Cheng-Ting Hsu,et al.  Capacity expansion planning of distribution substations considering PV penetration , 2012, 48th IEEE Industrial & Commercial Power Systems Conference.

[6]  Frequency independent automatic input variable selection for Neural Networks for forecasting , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[7]  Peter Mark Jansson,et al.  Performance measurement of amorphous and monocrystalline silicon PV modules in Eastern U.S. Energy production versus ambient and module temperature , 2009, 2009 IEEE Instrumentation and Measurement Technology Conference.

[8]  Dorine A. J. Burmantje.  Plenary Session 2 - Co-operation between Land Administration and SDI Keynote presentation Spatial Data Infrastructures and Land Administration in Europe Dorine A. J. BURMANTJE, Chair of the Board Dutch Cadastre, Land Registry and Mapping Agency, The Netherlands , 2005 .

[9]  Holger R. Maier,et al.  Efficient selection of inputs for artificial neural network models , 2005 .

[10]  Joab R Winkler,et al.  Numerical recipes in C: The art of scientific computing, second edition , 1993 .

[11]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[12]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[13]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[14]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .